OSS RadarPolyStrata alternatives
VecSzn/PolyStrata (124 stars, +84 this week): Run large AI models on your own PC: Qwen3.8-Flash-Next, GLM 5.3 Flash, Qwen3.6, Ornith 1.5 and Gemma 4. Why it matters: useful plumbing for shipping LLM-powered features.
Below are 12 other LLM tooling repos tracked by OSS Radar that share at least two GitHub topics with PolyStrata, ordered by how many topics overlap, then by stars gained in the last 7 days. Topic overlap means a similar problem space, not a drop-in replacement, so check each project's README.
1. mw00/project-maya
+210/wkest.Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Why it matters: useful plumbing for shipping LLM-powered features.
877 stars · C++ · shared topics: cuda, glm, llm, local-llm, mixture-of-experts, openai-api, self-hosted
2. ollama/ollama
+599/wkest.Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. Why it matters: useful plumbing for shipping LLM-powered features.
183k stars · Go · shared topics: gemma, glm, llm, qwen
3. unslothai/unsloth
+294/wkest.Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. Why it matters: useful plumbing for shipping LLM-powered features.
78k stars · Python · shared topics: gemma, llm, qwen, self-hosted
4. sgl-project/sglang
+256/wkest.SGLang is a high-performance serving framework for large language models and multimodal models. Why it matters: useful plumbing for shipping LLM-powered features.
37k stars · Python · shared topics: cuda, glm, llm, qwen
5. huggingface/transformers
+112/wkest.🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models… Why it matters: useful plumbing for shipping LLM-powered features.
168k stars · Python · shared topics: gemma, glm, llm, qwen
6. syv-ai/HyperQwen
+98/wkest.Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the… Why it matters: useful plumbing for shipping LLM-powered features.
2k stars · Python · shared topics: cuda, local-llm, qwen, speculative-decoding
7. MakazhanAlpamys/Soup
+718/wkest.Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. Why it matters: useful plumbing for shipping LLM-powered features.
9.1k stars · Python · shared topics: gguf, llm, local-llm
8. vllm-project/vllm
+375/wkest.A high-throughput and memory-efficient inference and serving engine for LLMs. Why it matters: useful plumbing for shipping LLM-powered features.
94k stars · Python · shared topics: cuda, llm, qwen
9. hiyouga/LlamaFactory
+130/wkest.Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024). Why it matters: useful plumbing for shipping LLM-powered features.
75k stars · Python · shared topics: gemma, llm, qwen
10. FareedKhan-dev/kimi-k3-in-c
+81/wkest.A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU. Why it matters: useful plumbing for shipping LLM-powered features.
9.1k stars · C · shared topics: inference-engine, llm, mixture-of-experts
11. KKKKhazix/AIHOT
+868/wkest.A website framework that collects hot topics from your sources and writes daily reports for any industry. Why it matters: useful plumbing for shipping LLM-powered features.
7.8k stars · TypeScript · shared topics: llm, self-hosted
12. Folkbench/folkbench
+868/wkest.Desktop app that switches Claude Code, Codex and other tools between AI API relays, showing their uptime and latency. Why it matters: useful plumbing for shipping LLM-powered features.
1.1k stars · Rust · shared topics: llm, openai-api
More: all trending LLM tooling repos · compare PolyStrata with the top 2